From: lm@mcvoy.com (Larry McVoy)
Subject: [TUHS] signals and blocked in I/O
Date: Fri, 1 Dec 2017 15:09:34 -0800 [thread overview]
Message-ID: <20171201230934.GA24335@mcvoy.com> (raw)
In-Reply-To: <20171201230302.0DC351FA41@orac.inputplus.co.uk>
On Fri, Dec 01, 2017 at 11:03:02PM +0000, Ralph Corderoy wrote:
> Hi Larry,
>
> > > So OOM code kills a (random) process in hopes of freeing up some
> > > pages but if this process is stuck in diskIO, nothing can be freed
> > > and everything grinds to a halt.
> >
> > Yep, exactly.
>
> Is that because the pages have been dirty for so long they've reached
> the VM-writeback timeout even though there's no pressure to use them for
> something else? Or has that been lengthened because you don't fear
> power loss wiping volatile RAM?
I'm tinkering with the pageout daemon so I'm trying to apply memory
pressure. I have 10 25GB processes (25GB malloced) and the processes just
walk the memory over and over. This is on a 256GB main memory machine
(2 socket haswell, 28 cpus, 28 1TB SSDs, on loan from Netflix).
It's the old "10 pounds of shit in a 5 pound bag" problem, same old stuff,
just a bigger bag.
The problem is that OOM can't kill the processes that are the problem,
they are stuck in disk wait. That's why I started asking why can't you
kill a process that's in the middle of I/O.
next prev parent reply other threads:[~2017-12-01 23:09 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-12-01 15:44 Larry McVoy
2017-12-01 15:53 ` Dan Cross
2017-12-01 16:11 ` Clem Cole
2017-12-01 16:18 ` Larry McVoy
2017-12-01 16:33 ` Warner Losh
2017-12-01 17:26 ` Larry McVoy
2017-12-01 19:10 ` Chris Torek
2017-12-01 23:21 ` Dave Horsfall
2017-12-01 21:33 ` Bakul Shah
2017-12-01 22:38 ` Larry McVoy
2017-12-01 23:03 ` Ralph Corderoy
2017-12-01 23:09 ` Larry McVoy [this message]
2017-12-01 23:42 ` Bakul Shah
2017-12-02 0:48 ` Larry McVoy
2017-12-02 1:40 ` Bakul Shah
2017-12-03 13:50 ` Ralph Corderoy
2017-12-04 16:36 ` arnold
2017-12-04 16:58 ` Arthur Krewat
2017-12-04 17:19 ` Warner Losh
2017-12-05 2:12 ` Bakul Shah
2017-12-04 22:07 ` Dave Horsfall
2017-12-04 22:54 ` Ron Natalie
2017-12-04 22:56 ` Warner Losh
2017-12-05 0:49 ` Dave Horsfall
2017-12-05 0:58 ` Arthur Krewat
2017-12-05 2:15 ` Dave Horsfall
2017-12-05 2:54 ` Clem cole
2017-12-02 14:59 ` Theodore Ts'o
2017-12-01 16:01 ` Dave Horsfall
2017-12-01 16:24 ` Warner Losh
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20171201230934.GA24335@mcvoy.com \
--to=lm@mcvoy.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).